Animated Representation of Facial Expression

1. A method, comprising: receiving, by a device, a plurality of image frames comprising a facial expression of a person; receiving, by the device, depth information comprising the facial expression of the person; determining, by the device, the facial expression of the person based on the plurality of image frames and the depth information; animating, by the device, an avatar based at least in part on the facial expression of the person; causing a first version of the animated avatar to be rendered, by the device, based on the facial expression; transmitting recipient information and the rendered first version of the animated avatar from the device to a message system for transmission to a recipient computing device associated with the recipient information; receiving, at the device, a response from the message system prior to delivery of the rendered first version of the animated avatar to the recipient computing device; causing, following the response from the message system, a second version of the animated avatar to be rendered at the device based on the facial expression, the second version corresponding to one or more capabilities of the recipient computing device associated with the recipient information; and transmitting the rendered second version of the animated avatar from the device to the recipient computing device without transmitting the first version of the animated avatar from the device to the recipient computing device.

2. The method of claim 1 , wherein the transmitting comprises: transmitting the rendered second version of the animated avatar with a metadata tag that enables the recipient computing device to loop playback of the animated avatar multiple times.

3. The method of claim 1 , wherein receiving the depth information comprises: receiving a plurality of depth frames that correspond to the plurality of image frames comprising the facial expression of the person, wherein the plurality of image frames and the plurality of depth frames are synchronized, and wherein the synchronization comprises aligning the plurality of image frames and the plurality of depth frames in time such that an image frame and a depth frame that are aligned in time comprise a key frame, and one or more key frames are interleaved by one or more image information frames.

4. The method of claim 1 , wherein the messaging system includes one or more identity servers and one or more message servers.

5. The method of claim 1 , further comprising: receiving a plurality of audio frames associated with the facial expression of the person; and aligning the plurality of audio frames in time with the plurality of image frames, wherein animating the avatar comprises adding audio based on the plurality of audio frames.

6. The method of claim 1 , wherein a movement of the person that is separate from the facial expression of the person causes an animated effect to be applied to the avatar.

7. The method of claim 1 , wherein the avatar corresponds to an object other than the person.

8. The method of claim 7 , wherein the object is an animal.

9. The method of claim 1 , wherein the first version is rendered based on one or more properties of a sender device, and wherein the second version is rendered based on one or more properties of the recipient computing device.

10. A non-transitory computer readable medium programmed with instructions that, when executed by a processing system, perform operations, comprising: receiving, by a device, a plurality of image frames comprising a facial expression of a person; receiving, by the device, depth information comprising the facial expression of the person; determining, by the device, the facial expression of the person based on the plurality of image frames and the depth information; animating, by the device, an avatar based at least in part on the facial expression of the person in the plurality of image frames; causing a first version of the animated avatar to be rendered, by the device, based on the facial expression; transmitting recipient information and the rendered first version of the animated avatar to from the device to a message system for transmission to a recipient computing device associated with the recipient information; receiving, at the device, a response from the message system prior to delivery of the rendered first version of the animated avatar to the recipient computing device; causing, following the response, a second version of the animated avatar to be rendered at the device based on the facial expression, the second version corresponding to one or more capabilities of the recipient computing device associated with the recipient information; and transmitting the rendered second version of the animated avatar from the device to the recipient computing device without transmitting the first version of the animated avatar from the device to the recipient computing device.

11. The non-transitory computer readable medium of claim 10 , wherein the transmitting comprises: transmitting the rendered second version of the animated avatar with a metadata tag that enables the recipient computing device to loop playback of the animated avatar multiple times.

12. The non-transitory computer readable medium of claim 10 , the receiving the depth information comprising: receiving a plurality of depth frames comprising the facial expression of the person, wherein the plurality of image frames and the plurality of depth frames are synchronized, and wherein the synchronization comprises aligning the plurality of image frames and the plurality of depth frames in time such that an image frame and a depth frame that are aligned in time comprise a key frame, and one or more key frames are interleaved by one or more image information frames.

13. The non-transitory computer readable medium of claim 10 , wherein the messaging system includes one or more identity servers and one or more message servers.

14. The non-transitory computer readable medium of claim 10 , the operations further comprising: receiving a plurality of audio frames associated with the facial expression of the person; and aligning the plurality of audio frames in time with the plurality of image frames, wherein animating the avatar comprises adding audio based on the plurality of audio frames.

15. The non-transitory computer readable medium of claim 10 , wherein a movement of the person that is separate from the facial expression of the person causes an animated effect to be applied to the avatar.

16. The non-transitory computer readable medium of claim 10 , wherein the first version is rendered based on one or more properties of a sender device comprising the processing system, and wherein the second version is rendered based on one or more properties of the recipient computing device.

17. A device comprising: a processing system coupled to a memory programmed with executable instructions that, when executed by the processing system perform operations, the operations comprising: receiving a plurality of image frames comprising a facial expression of a person; receiving depth information comprising the facial expression of the person; determining the facial expression of the person based on the plurality of image frames and the depth information; generating an animated avatar based at least in part on the facial expression of the person in the plurality of image frames; causing a first version of the animated avatar to be rendered based on the facial expression; transmitting recipient information and the rendered first version of the animated avatar to a message system for transmission to a recipient computing device associated with the recipient information; receiving, from the message system, a response prior to delivery of the rendered first version of the animated avatar to the recipient computing device; causing, following the response, a second version of the animated avatar to be rendered based on the facial expression, the second version corresponding to one or more capabilities of the recipient computing device associated with the recipient information; and transmitting the rendered second version of the animated avatar to the recipient computing device without transmitting the first version of the animated avatar from the device to the recipient computing device.

18. The device of claim 17 , wherein the transmitting comprises: transmitting the rendered second version of the animated avatar with a metadata tag that enables a receiving computing device to loop playback of the animated avatar multiple times.

19. The device of claim 17 , wherein a movement of the person that is identified separately from the facial expression of the person causes an animated effect to be applied to the avatar.

20. The device of claim 17 , wherein the first version is rendered based on one or more properties of the processing system, and wherein the second version is rendered based on one or more properties of the recipient computing device.